import pandas as pd
import matplotlib.pyplot as plt

ratings = pd.read_csv("FilmData2.csv")

ratings.head()

	Hulu	Netflix	Amazon	DisneyPlus	type	title	release_year	region	language	tconst	...	primaryTitle	originalTitle	isAdult	startYear	endYear	runtimeMinutes	genres	tconst-1	averageRating	numVotes
0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt4048280	...	RED WINDOWS	Red Windows	0	2016	\N	NaN	Thriller	tt4048280	2.5	21
1	NaN	NaN	NaN	NaN	NaN	NaN	NaN	\N	\N	tt4048280	...	RED WINDOWS	Red Windows	0	2016	\N	NaN	Thriller	tt4048280	2.5	21
2	NaN	NaN	NaN	NaN	NaN	NaN	NaN	GB	\N	tt3335210	...	WHAT GOES UP	What Goes Up	0	2014	\N	87.0	Comedy,Romance,Sci-Fi	tt3335210	2.5	23
3	NaN	NaN	NaN	NaN	NaN	NaN	NaN	\N	\N	tt3335210	...	WHAT GOES UP	What Goes Up	0	2014	\N	87.0	Comedy,Romance,Sci-Fi	tt3335210	2.5	23
4	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt3335210	...	WHAT GOES UP	What Goes Up	0	2014	\N	87.0	Comedy,Romance,Sci-Fi	tt3335210	2.5	23

5 rows × 21 columns

vals = ratings[(ratings['titleType']=='movie') & (ratings['genres']!='\\N') & (ratings['region']=='US')] 
vals = vals[vals['numVotes']>100]

vals.head()

	Hulu	Netflix	Amazon	DisneyPlus	type	title	release_year	region	language	tconst	...	primaryTitle	originalTitle	isAdult	startYear	endYear	runtimeMinutes	genres	tconst-1	averageRating	numVotes
47	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt4412218	...	RUNNING MAN	Benpao Ba! Xiongdi	0	2015	\N	88.0	Action,Comedy,Documentary	tt4412218	2.5	115
55	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt4253170	...	THE APOSTLES	Gui zhen	0	2013	\N	91.0	Fantasy,Horror,Sci-Fi	tt4253170	2.5	133
58	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt4679576	...	BLOODHOUND	Bloodhound	0	2020	\N	72.0	Crime,Drama	tt4679576	2.5	135
65	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt4591226	...	THE LAST HOUSE	The Last House	0	2015	\N	91.0	Horror	tt4591226	2.5	155
67	NaN	NaN	NaN	NaN	NaN	NaN	NaN	US	\N	tt2757592	...	A TALKING PONY!?!	A Talking Pony!?!	0	2013	\N	88.0	Comedy,Family,Fantasy	tt2757592	2.5	184

5 rows × 21 columns

genres = []

for genre in vals["genres"]:
    # split all
    _temp = genre.split(",")
    for item in _temp:
        if item not in genres:
            genres.append(item)

genres

['Action',
 'Comedy',
 'Documentary',
 'Fantasy',
 'Horror',
 'Sci-Fi',
 'Crime',
 'Drama',
 'Family',
 'Thriller',
 'Mystery',
 'Adventure',
 'Animation',
 'Romance',
 'Sport',
 'Music',
 'Biography',
 'Western',
 'War',
 'Reality-TV',
 'History',
 'Musical',
 'News',
 'Talk-Show',
 'Adult',
 'Short']

df = vals['averageRating']

df.shape

(57592,)

import plotly 
import plotly.express as px

fig = px.histogram(data_frame=vals, x=vals["averageRating"], title="IMDB Scores of the Programs")
fig.show()

fig = px.box(data_frame=vals, x=vals["averageRating"])
fig.update_traces(overwrite=False)
fig.show()

vals[["averageRating", "runtimeMinutes"]].corr()

	averageRating	runtimeMinutes
averageRating	1.000000	0.025417
runtimeMinutes	0.025417	1.000000

top_10_ratings = vals[["averageRating", "title", "genres", "startYear"]].sort_values(["averageRating"], ascending=False)[:10]
top_10_ratings
fig = px.scatter(top_10_ratings, y= 'title', x='averageRating', hover_data = top_10_ratings[['genres','startYear']], color='genres', 
                 title = "Top 10 High Rated Programs")
fig.show()

vals[["averageRating", "startYear"]].corr()

	averageRating	startYear
averageRating	1.000000	-0.016972
startYear	-0.016972	1.000000

plotdata = pd.DataFrame(vals["averageRating"])

vals.groupby('startYear', as_index=False)['averageRating'].mean()

fig = px.bar(data_frame=vals, x=vals["startYear"],y=vals["averageRating"])
fig.show()

df2 = vals.groupby('startYear', as_index=False)['averageRating'].mean()

fig = px.bar(data_frame=df2, x=df2["startYear"],y=df2["averageRating"])
fig.show()

df3 = vals.groupby('genres', as_index=False)['averageRating'].mean()
fig = px.bar(data_frame=df3, x=df3["genres"],y=df3["averageRating"])
fig.show()